Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4218 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.3302. Min Act: -0.0000

Data Index: 430427 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.0969. Min Act: -0.0000

Data Index: 1067569 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.1432. Min Act: -0.0000

Data Index: 133194 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.0662. Min Act: -0.0000

Data Index: 718933 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 1.3302. Min Range: -1.3302

Max Act: 1.0077. Min Act: -0.0000

Data Index: 817634 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.9431. Min Act: -0.0000

Data Index: 846489 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.8233. Min Act: -0.0000

Data Index: 382665 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.9093. Min Act: -0.0000

Data Index: 496438 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.9325. Min Act: 0.0000

Data Index: 673596 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.9158. Min Act: 0.0000

Data Index: 111768 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.8969. Min Act: -0.0000

Data Index: 1199153 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.9025. Min Act: -0.0000

Data Index: 149592 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.9264. Min Act: -0.0000

Data Index: 566778 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.9254. Min Act: 0.0000

Data Index: 151083 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.8879. Min Act: -0.0000

Data Index: 571512 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.8470. Min Act: -0.0000

Data Index: 469155 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.8567. Min Act: -0.0000

Data Index: 574009 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.8736. Min Act: -0.0000

Data Index: 890703 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1040745 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 1.3302. Min Range: -1.3302

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1224598 (C4 (Web Text))

Max Activating Token Index: 454